Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5311
    Prev
    Next
    INDEX
    Explanations

    cooking methods and food preparation techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.69
    Personendaten
    -0.59
     AttributeSet
    -0.59
    webElementXpaths
    -0.57
    
    -0.56
    principalColumn
    -0.56
     Италијани
    -0.55
    featureID
    -0.55
    ритори
    -0.52
    VersionUID
    -0.50
    POSITIVE LOGITS
     roasting
    0.51
    mybatisplus
    0.50
     cooked
    0.49
     burnt
    0.49
    burnt
    0.48
     roasted
    0.48
     Burnt
    0.47
     baked
    0.45
    cooked
    0.45
     oven
    0.45
    Activations Density 0.435%

    No Known Activations